autocontext

<!-- autocontext-readme-hero:start --> <p align="center"> <img src="autocontext/assets/banner.svg" alt="autocontext ASCII banner" /> </p> <p align="center"><strong>closed-loop control plane for agent improvement</strong></p> <!-- autocontext-readme-hero:end -->

autocontext is a closed-loop control plane for improving agent behavior over repeated runs.

It executes tasks, evaluates outcomes, updates persistent knowledge, and can distill successful behavior into cheaper local runtimes. The goal is to move from frontier-model exploration toward validated, reusable, lower-cost execution.

Why It Exists

Most agent systems start every run cold. They do not reliably carry forward what worked, what failed, and what should change next.

autocontext adds that missing feedback loop:

• run the task
• analyze what happened
• persist validated lessons
• use those lessons in the next run
• optionally train and route to local models when the task is stable enough

How It Works

Each generation runs through a structured multi-agent loop:

• competitor proposes a strategy or artifact for the task
• analyst explains what happened and why
• coach turns that analysis into playbook updates and future hints
• architect proposes tools, harness improvements, or structural changes
• curator gates what knowledge is allowed to persist

Strategies are then evaluated through scenario execution, staged validation, and gating. Weak changes are rolled back. Successful changes accumulate into reusable knowledge.

Choose An Entry Point

• Want the full control plane, dashboard, scenario runner, and training loop? Start with the Python package in .

<!-- autocontext-whats-new:start --> <!-- autocontext-whats-new:end -->